Beam 1.0
| Released | 2026-10-05 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 55.7 · rank 70 |
| Provider | Reflection |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 55.7 | 70 | 18 |
| Overall: Coding | 55.5 | 65 | 16 |
| Overall: Reasoning | 55.7 | 69 | 7 |
| Overall: Agentic work | 56.3 | 69 | 15 |
| Overall: Frontend | 55.3 | 59 | 4 |
| Coding | 54.8 | 77 | 3 |
| Agents | 56.9 | 63 | 7 |
| Reasoning | 56.8 | 71 | 5 |
| Math | 54.7 | 74 | 1 |
| Knowledge | 55.0 | 60 | 1 |
| Frontend | 55.5 | 52 | 1 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 55.5 ±1.9 | 15 |
| High | 54.7 ±5.7 | 2 |
| Low | 48.4 ±5.7 | 2 |
| Max | 58.5 ±5.5 | 1 |
| Medium | 51.0 ±5.7 | 2 |
| Extra High | 55.5 ±5.7 | 2 |
Evidence
Coding 54.8 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Code Migration v1.1 | 22.8% | Vals AI | 2026-11-09 |
| IOI | 22.8% | Vals AI | 2026-10-29 |
| SciCode | 48.5% | Epoch AI | 2026-11-11 |
Agents 56.9 ±1.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 4.0% | Vals AI | 2026-11-09 |
| Terminal-Bench-Science | 1.4% | Vals AI | 2026-11-09 |
| APEX-Agents | 48.8% | Epoch AI | 2026-11-11 |
| EMB v1.1 (Excel financial modeling) | 64.7% | Vals AI | 2026-11-09 |
| Tax Agent Bench | 8.8% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 51.8% | Vals AI | 2026-11-09 |
| HLAB-Vals 1.1 (legal agent) | 4.6% | Vals AI | 2026-11-09 |
Reasoning 56.8 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MysteryMechanism | 22.1% | Vals AI | 2026-11-09 |
| ARC-AGI-2 | 23.5% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 23.5% | ARC Prize | 2026-11-11 |
| CritPt | 13.1% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 74.0% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 74.0% | Epoch AI | 2026-11-11 |
| BioMysteryBench | 42.6% | Vals AI | 2026-11-09 |
Math 54.7 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ProofBench v1.1 | 18.0% | Vals AI | 2026-11-09 |
| ProofBench | 18.0% | Epoch AI | 2026-11-11 |
Knowledge 55.0 ±6.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Legal Research Bench | 28.8% | Vals AI | 2026-11-09 |
Frontend 55.5 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 66.4% | Vals AI | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 67.7% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 55.7% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 45.0% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 67.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 55.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 45.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 20.0% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 6.4% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 2.8% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 20.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 6.4% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 2.8% | ARC Prize | A stronger configuration result was used |
Names matched to this model
beam-1-0